Learning inertial odometry for dynamic legged robot state estimation
This paper introduces a novel proprioceptive state estimator for legged robots based on a learned displacement measurement from IMU data. Recent research in pedestrian tracking has shown that motion can be inferred from inertial data using convolutional neural networks. A learned inertial displaceme...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Journal of Machine Learning Research
2022
|
| _version_ | 1826275630974500864 |
|---|---|
| author | Buchanan, R Camurri, M Dellaert, F Fallon, M |
| author_facet | Buchanan, R Camurri, M Dellaert, F Fallon, M |
| author_sort | Buchanan, R |
| collection | OXFORD |
| description | This paper introduces a novel proprioceptive state estimator for legged robots based on a learned displacement measurement from IMU data. Recent research in pedestrian tracking has shown that motion can be inferred from inertial data using convolutional neural networks. A learned inertial displacement measurement can improve state estimation in challenging scenarios where leg odometry is unreliable, such as slipping and compressible terrains. Our work learns to estimate a displacement measurement from IMU data which is then fused with traditional leg odometry. Our approach greatly reduces the drift of proprioceptive state estimation, which is critical for legged robots deployed in vision and lidar denied environments such as foggy sewers or dusty mines. We compared results from an EKF and an incremental fixed-lag factor graph estimator using data from several real robot experiments crossing challenging terrains. Our results show a reduction of relative pose error by 37% in challenging scenarios when compared to a traditional kinematic-inertial estimator without learned measurement. We also demonstrate a 22% reduction in error when used with vision systems in visually degraded environments such as an underground mine. |
| first_indexed | 2024-03-06T23:01:44Z |
| format | Conference item |
| id | oxford-uuid:625a6aa9-b992-4e78-938b-8a3db5f90135 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T23:01:44Z |
| publishDate | 2022 |
| publisher | Journal of Machine Learning Research |
| record_format | dspace |
| spelling | oxford-uuid:625a6aa9-b992-4e78-938b-8a3db5f901352022-03-26T18:05:47ZLearning inertial odometry for dynamic legged robot state estimationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:625a6aa9-b992-4e78-938b-8a3db5f90135EnglishSymplectic ElementsJournal of Machine Learning Research2022Buchanan, RCamurri, MDellaert, FFallon, MThis paper introduces a novel proprioceptive state estimator for legged robots based on a learned displacement measurement from IMU data. Recent research in pedestrian tracking has shown that motion can be inferred from inertial data using convolutional neural networks. A learned inertial displacement measurement can improve state estimation in challenging scenarios where leg odometry is unreliable, such as slipping and compressible terrains. Our work learns to estimate a displacement measurement from IMU data which is then fused with traditional leg odometry. Our approach greatly reduces the drift of proprioceptive state estimation, which is critical for legged robots deployed in vision and lidar denied environments such as foggy sewers or dusty mines. We compared results from an EKF and an incremental fixed-lag factor graph estimator using data from several real robot experiments crossing challenging terrains. Our results show a reduction of relative pose error by 37% in challenging scenarios when compared to a traditional kinematic-inertial estimator without learned measurement. We also demonstrate a 22% reduction in error when used with vision systems in visually degraded environments such as an underground mine. |
| spellingShingle | Buchanan, R Camurri, M Dellaert, F Fallon, M Learning inertial odometry for dynamic legged robot state estimation |
| title | Learning inertial odometry for dynamic legged robot state estimation |
| title_full | Learning inertial odometry for dynamic legged robot state estimation |
| title_fullStr | Learning inertial odometry for dynamic legged robot state estimation |
| title_full_unstemmed | Learning inertial odometry for dynamic legged robot state estimation |
| title_short | Learning inertial odometry for dynamic legged robot state estimation |
| title_sort | learning inertial odometry for dynamic legged robot state estimation |
| work_keys_str_mv | AT buchananr learninginertialodometryfordynamicleggedrobotstateestimation AT camurrim learninginertialodometryfordynamicleggedrobotstateestimation AT dellaertf learninginertialodometryfordynamicleggedrobotstateestimation AT fallonm learninginertialodometryfordynamicleggedrobotstateestimation |